{"id":"https://openalex.org/W7164516179","doi":"https://doi.org/10.48550/arxiv.2606.12679","title":"Fed-FBD: Federated Functional Block Diversification for Isolation, Privacy, and Surgical Unlearning","display_name":"Fed-FBD: Federated Functional Block Diversification for Isolation, Privacy, and Surgical Unlearning","publication_year":2026,"publication_date":"2026-06-10","ids":{"openalex":"https://openalex.org/W7164516179","doi":"https://doi.org/10.48550/arxiv.2606.12679"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.12679","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.12679","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2606.12679","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5138551541","display_name":"Weijie Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Weijie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5133624135","display_name":"Alan B. McMillan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"McMillan, Alan B.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.7441999912261963,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.7441999912261963,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.15539999306201935,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.014800000004470348,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.7153000235557556},{"id":"https://openalex.org/keywords/modular-design","display_name":"Modular design","score":0.5972999930381775},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.5673999786376953},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.5464000105857849},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.436599999666214},{"id":"https://openalex.org/keywords/diversification","display_name":"Diversification (marketing strategy)","score":0.3578999936580658},{"id":"https://openalex.org/keywords/hacker","display_name":"Hacker","score":0.3255000114440918}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7170000076293945},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.7153000235557556},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.5972999930381775},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.5673999786376953},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.5464000105857849},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.436599999666214},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43529999256134033},{"id":"https://openalex.org/C180916674","wikidata":"https://www.wikidata.org/wiki/Q3711935","display_name":"Diversification (marketing strategy)","level":2,"score":0.3578999936580658},{"id":"https://openalex.org/C86844869","wikidata":"https://www.wikidata.org/wiki/Q2798820","display_name":"Hacker","level":2,"score":0.3255000114440918},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.3248000144958496},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3163999915122986},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.3154999911785126},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.3093999922275543},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3034000098705292},{"id":"https://openalex.org/C12590798","wikidata":"https://www.wikidata.org/wiki/Q3933199","display_name":"Replication (statistics)","level":2,"score":0.29019999504089355},{"id":"https://openalex.org/C199521495","wikidata":"https://www.wikidata.org/wiki/Q181487","display_name":"Audit","level":2,"score":0.28349998593330383},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.2806999981403351},{"id":"https://openalex.org/C94966114","wikidata":"https://www.wikidata.org/wiki/Q29256","display_name":"Black box","level":2,"score":0.26829999685287476},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2590999901294708},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.25220000743865967}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.12679","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.12679","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2606.12679","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.12679","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Federated":[0],"learning":[1],"(FL)":[2],"enables":[3],"collaborative":[4],"model":[5],"training":[6],"without":[7,146],"sharing":[8],"raw":[9],"patient":[10],"data,":[11],"but":[12],"standard":[13],"approaches":[14],"such":[15],"as":[16,21],"FedAvg":[17,180],"treat":[18],"each":[19,83],"client":[20,109],"a":[22,39,53,59,77,138,162],"black":[23],"box":[24],"and":[25,71,75,88,132,145,156,189],"provide":[26],"no":[27],"mechanism":[28,129],"for":[29,173],"isolating":[30],"an":[31,105],"adversarial":[32,106,193],"contributor,":[33],"auditing":[34],"per-client":[35],"influence,":[36],"or":[37,107],"honoring":[38],"departed":[40,139],"participant's":[41,140],"right":[42],"to":[43,197],"be":[44],"forgotten.":[45],"We":[46],"present":[47],"Fed-FBD":[48,91,160],"(Federated":[49],"Functional":[50],"Block":[51],"Diversification),":[52],"modular":[54],"federated":[55],"architecture":[56],"that":[57,104,159],"decomposes":[58],"ResNet":[60],"backbone":[61],"into":[62],"six":[63,150,192],"functional":[64],"blocks":[65,202],"(the":[66],"stem,":[67],"four":[68,187],"residual":[69],"groups,":[70],"the":[72,112,169,198,210],"classification":[73],"head)":[74],"maintains":[76],"warehouse":[78],"of":[79,137,179,186],"N":[80],"color":[81],"variants,":[82],"assembled":[84],"from":[85,124],"independently":[86],"tracked":[87],"contributor-stamped":[89],"blocks.":[90],"provides":[92],"three":[93,185],"capabilities":[94],"absent":[95],"in":[96],"FedAvg:":[97],"(i)":[98],"architecturally":[99],"guaranteed":[100],"block-level":[101],"isolation,":[102],"so":[103],"mislabelled":[108],"cannot":[110],"contaminate":[111],"clean":[113,211],"colous;":[114],"(ii)":[115],"privacy-by-design,":[116],"where":[117],"membership":[118],"inference":[119],"advantage":[120],"is":[121,130],"already":[122],"indistinguishable":[123],"chance":[125],"before":[126],"any":[127],"privacy":[128],"applied;":[131],"(iii)":[133],"surgical":[134],"machine":[135],"unlearning":[136],"contribution":[141],"at":[142,154,181,204],"sub-second":[143],"cost":[144],"retraining.":[147],"Experiments":[148],"on":[149,168,184,209],"MedMNIST-2D":[151],"datasets,":[152,188],"PathMNIST":[153],"224x224,":[155],"CIFAR-10":[157],"show":[158],"trades":[161],"modest":[163],"0.3%-3.1%":[164],"IID":[165],"accuracy":[166],"gap":[167],"adequately":[170],"sized":[171],"datasets":[172],"these":[174],"guarantees,":[175],"remains":[176],"within":[177],"0.8%-4.0%":[178],"Dirichlet":[182],"alpha=1.0":[183],"confines":[190],"all":[191],"attacks":[194],"we":[195],"study":[196],"poisoned":[199],"client's":[200],"own":[201],"with":[203],"most":[205],"+/-0.01":[206],"AUC":[207],"drift":[208],"colors.":[212]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-06-13T00:00:00"}